These studies have used a Bayes factor (BF) analysis and might be used as examples. Please note: We did not review the provided code or the papers, and this list is not to be meant as an endorsement. Please use with care.
A list of "official" examples for the usage of the BFDA package can be found in our manual and in the supplemental material of our tutorial paper.
| Paper | Year | Context | Test Design | Reproducible script |
|---|---|---|---|---|
| Thompson, W. B., & Radell, M. L. (2021). Acceptance of anomalous research findings: Explaining treatment implausibility reduces belief in far-fetched results. PeerJ, 9, e12532. https://doi.org/10.7717/peerj.12532 | 2021 | "The study used a 2 (treatment plausibility) ×3 (results type) between-subjects factorial design. [...] Participants were randomly assigned to conditions (n = 100 per condition). We conducted a priori power analyses for detecting differences between any two combinations of treatments. This sample size yielded statistical power of 94% using traditional power analysis ([Cohen, 1988](https://scholar.google.com/scholar_lookup?title=Statistical power analysis for the behavioral sciences&author=Cohen&publication_year=1988)), assuming a two-sided alpha level of .05 and a moderate effect (d = 0.50). A Bayesian design analysis ([Stefan et al., 2019](https://scholar.google.com/scholar_lookup?title=A tutorial on Bayes factor design analysis using an informed prior&author=Stefan&publication_year=2019)) indicated a 79% probability of obtaining a Bayes factor larger than 10." | fixed N | not provided |
| Boayue, N. M., Csifcsák, G., Aslaksen, P., Turi, Z., Antal, A., Groot, J., ... & Mittner, M. (2020). Increasing propensity to mind‐wander by transcranial direct current stimulation? A registered report. European Journal of Neuroscience. https://doi.org/10.1111/ejn.14347 | 2020 | "Following Kruschke (2014), we ran a Bayesian power analysis where our primary goal was to exclude the null hypothesis of an effect size of d = 0 from the posterior 95% highest-density interval in the positive direction." (p. 763) | sequential BFs with minimum and maximum N | https://osf.io/srwe6/ |
| Field, S. M., Wagenmakers, E. J., Kiers, H. A., Hoekstra, R., Ernst, A. F., & van Ravenzwaaij, D. (2020). The effect of preregistration on trust in empirical research findings: results of a registered report. Royal Society Open Science. https://doi.org/10.1098/rsos.181351 | 2020 | "We are grateful for Angelika Stefan’s assistance with conducting a custom Bayes Factor Design Analysis for ANOVA." (p. 14) | fixed N | https://osf.io/zcygh/ |
| Parma, V., Ohla, K., Veldhuizen, M. G., Niv, M. Y., Kelly, C. E., Bakke, A. J., ... & Hayes, J. E. (2020). More than smell—COVID-19 is associated with severe impairment of smell, taste, and chemesthesis. Chemical Senses. https://doi.org/10.1093/chemse/bjaa041 | 2020 | "We derived the minimal Nmin = 480 per group to start SBFD through a Bayes Factor Design Analysis (BFDA) for fixed-n designs (Schönbrodt and Wagenmakers, 2018) for a two-independent-sample, two-sided testing, and a conservative Cohen’s D = 0.2 with 80% power of reaching a BF10 > 10 and a BF01 > 6 with a default prior." (p. 614) | sequential BFs with minimum N | not provided |
| Pereg, M., Meiran, N. (2020). Power of instructions for task implementation: superiority of explicitly instructed over inferred rules. Psychological Research. https://doi.org/10.1007/s00426-020-01293-5 | 2020 | "Additionally, we used the BFDA package for Bayesian design analysis (Schönbrodt & Wagenmakers, 2018). We assumed a modest effect size (Cohen’s d = 0.5) for the difference between the experiments (i.e., a between-subjects analysis, N= 80), and the simulation reached 5.8% and 4.4% undecided results (for present/absent effect, respectively), with a rate of 4.9% false positive and 15.3% false negative." (p. 11) | fixed N | https://osf.io/srwe6/ |
| Płomecka, M. B., Barańczuk-Turska, Z., Pfeiffer, C., & Langer, N. (2020). Aging Effects and Test–Retest Reliability of Inhibitory Control for Saccadic Eye Movements. Eneuro. https://doi.org/10.1523/ENEURO.0459-19.2020 | 2020 | "Considering that the data to be used in this study is was recorded in our laboratory in the context of a larger project with a fixed number of participants [...], we used the simulation-based approach analysis design from Schönbrodt and Wagenmakers (2018) using the BFDA package (Schönbrodt & Wagenmakers, 2018)." (p. 3) | fixed N | not provided |
| Tzavella, L., Maizey, L., Lawrence, A. D., & Chambers, C. D. (2020). The affective priming paradigm as an indirect measure of food attitudes and related choice behaviour. Psychonomic bulletin & review. https://doi.org/10.3758/s13423-020-01764-1 | 2020 | "Although frequentist power analysis was not appropriate for an SBF design, a Bayes factor design analysis (BFDA; [...]) was conducted to assess the probability of the proposed design generating misleading evidence (Schönbrodt & Wagenmakers, 2018). [...] Only the BFDA results were considered for the design of the study, and no other power analyses were performed." (p. 5) | sequential BFs with minimum and maximum N | https://osf.io/xk9jc/ |
| Tzavella, L. (2020). Behavioural measures and training interventions for food-related cognition, motivation and affect (Doctoral dissertation, Cardiff University). http://orca.cf.ac.uk/id/eprint/129213 | 2020 | "Consistent with previous work [...], Bayes Factor Design Analysis (BFDA; Schönbrodt & Wagenmakers, 2018) was performed to assess the probability of the proposed SBF design generating misleading evidence for the primary hypotheses." (p. 164) | sequential BFs with minimum and maximum N | https://osf.io/d64ze/ |
| Allen, P. J., Fielding, J. L., East, E. C., Kay, R. H. S., Steele, C. S., & Breen, L. J. (2019). Using StatHand to train structural awareness and promote the development of statistic selection skills. Scholarship of Teaching and Learning in Psychology. https://doi.org/10.1037/stl0000177 | 2019 | "This effect size [d = 0.64] was used as the basis for a fixed-n Bayes Factor Design Analysis (BFDA; Schönbrodt & Wagenmakers, 2018), which indicated a .86 probability of observing Bayes Factors (BFs) > 3 [...] in a one-sided Bayesian independent samples t test. The probability of inconclusive or anecdotal evidence (BFs between 3 and .33) was estimated to be .14 while the probability of false negatives (BFs < .33) was <.01." (p. 3) | fixed N | not provided |
| Allen, P. J., Finlay, J., Roberts, L. D., & Baughman, F. D. (2019). An experimental evaluation of StatHand: A free application to guide students’ statistical decision making. Scholarship of Teaching and Learning in Psychology. https://doi.org/10.1037/stl0000132 | 2019 | "These effect sizes [d = 0.64/0.68] were used in fixed-n Bayes factor design analyses (BFDA; Schönbrodt & Wagenmakers, 2018), which indicated a .86/.83 probability of observing Bayes factors (BFs) > 3 [...] in our one-/two-sided Bayesian hypothesis tests." (p. 26) | fixed N | not provided |
| Heyman, T., Maerten, A. S., Vankrunkelsven, H., Voorspoels, W., & Moors, P. (2019). Sound-Symbolism Effects in the Absence of Awareness: A Replication Study. Psychological Science. https://doi.org/10.1177/0956797619875482 | 2019 | "To determine the necessary sample size, we performed a Bayes factor (BF) design analysis (Schönbrodt & Wagenmakers, 2018) More specifically, we opted for a sequential design with a maximal sample size, which entails that data be gathered until enough evidence has been accumulated or the predefined maximum number of participants has been tested." (p. 3) | sequential BFs with minimum and maximum N | https://osf.io/hzvrc/ |
| Keute, M. (2019). The neuropsychology of transcutaneous vagus nerve simulation. (Doctoral dissertation, University Magdeburg). http://dx.doi.org/10.25673/31909 | 2019 | "A simulation-based Bayes factor design analysis (Schönbrodt & Wagenmakers, 2018) found that given dz = 0.5 and n = 40, Bayes factors conclusively favored the working hypothesis (BF > 6) 76.5% of the time for the simulated data." (p. 96) | sequential BFs with minimum and maximum N | not provided |
| Montero-Melis, G., van Paridon, J., Ostarek, M., & Bylund, E. (2019). Does the motor system functionally contribute to keeping words in working memory? A pre-registered replication of Shebani and Pulvermüller (2013, Cortex; a stage 1 Registered Report). https://doi.org/10.31234/osf.io/pqf8k | 2019 | "We adopted a prospective Bayes factor design analysis to plan sample size (BFDA, Schönbrodt & Wagenmakers, 2018)." (p. 12) | sequential BFs with minimum and maximum N | https://osf.io/n9sa4/?view_only=63e3071ba35641a0ba11785324e427e3 |
| Ernst, A. F., Hoekstra, R., Wagenmakers, E. J., Gelman, A., & van Ravenzwaaij, D. (2018). Do researchers anchor their beliefs on the outcome of an initial study? Testing the time-reversal heuristic. Experimental psychology. https://doi.org/10.1027/1618-3169/a000402 | 2018 | "Given our available sample size of about 350 undergraduate students and a fixed modest effect size of Cohen’s d = .35, we undertook a Bayesian design analysis in order to determine the expected strength of evidence (Schönbrodt & Wagenmakers, 2016). The design analysis was performed using the R package BFDA (Schönbrodt, 2016). [...] This distribution reveals that with N = 350 and d = .35, a one-sided t-test has a 68% chance to reach a Bayes factor of 10 or higher in favor of the RAE hypothesis. If, on the other hand, no RAE effect exists (i.e., d = 0), our study on undergraduates would yield strong evidence against the RAE hypothesis in 42% of the cases, with associated Bayes factor values lower than 1/10." (p. 12) | fixed N | not provided |
| Hoogeveen, S., Wagenmakers, E. J., Kay, A. C., & Van Elk, M. (2018). Compensatory control and religious beliefs: a registered replication report across two countries. Comprehensive Results in Social Psychology. https://doi.org/10.1080/23743603.2019.1684821 | 2018 | "Our sampling plan was based on Bayes factor design analysis (BFDA; Schönbrodt & Wagenmakers, 2018; Stefan, Gronau, Schönbrodt, & Wagenmakers, 2019), a recently developed method to help balance informativeness and efficiency of planned experiments within a Bayesian framework." (p. 10) | fixed N | not provided |